registry / oh-my-claude-sisyphus / 5.7.26
oh-my-claude-sisyphus@5.7.26
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe postinstall hook only builds an optional native component on macOS. Jev’s external requests require a Typesafe key and configured judgment points, and the README documents the feature and states that unconfigured use has zero egress.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user configures a Typesafe API key and enables Jev judgment points; prompt-submit hooks can then query the service.
Impact
The service receives prompt-derived data for Jev’s orchestration judgments. No unauthorized credential transfer or other attack behavior was identified.
Mechanism
The CLI sends judgment state and questions to api.typesafe.ai/v1/systemone using the configured Typesafe key.
AI rationale
The postinstall hook only builds an optional native component on macOS. Jev’s external requests require a Typesafe key and configured judgment points, and the README documents the feature and states that unconfigured use has zero egress.
Network endpoints1
api.typesafe.ai/v1/systemone
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The postinstall hook skips non-macOS systems and only attempts to build the package’s optional native module on macOS.
- Jev requests require a Typesafe API key and configured judgment points; the README documents the setup and says unconfigured use has zero egress.
- When enabled, Jev sends judgment state and questions with the Typesafe key to its documented endpoint, api.typesafe.ai/v1/systemone.
- Prompt-submit hooks pass prompts to Jev’s judgment functions; those functions remain off unless the required key and judgment-point configuration are present.
Evidence against
- Configured Jev requests transmit prompt-derived state to an external service, so users who enable it send that data to Typesafe.
- The package includes a postinstall lifecycle hook that launches a local build script on macOS.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
Source & flagged code
24 flaggedpackage.jsonView file
•scripts.postinstall = node scripts/postinstall-contained-fs.mjs
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkgdist/autoresearch/runtime.jsView file
1import { execFileSync, spawnSync } from 'child_process';
L2: import { existsSync } from 'fs';
High
Child Process
Package source references child process execution.
dist/autoresearch/runtime.jsView on unpkg · L1371encoding: 'utf-8',
L372: shell: true,
L373: maxBuffer: 1024 * 1024,
High
Findings
1 Critical16 High8 Medium7 Low
CriticalPrevious Version Dangerous Deltadist/hooks/keyword-detector/index.js
HighInstall Time Lifecycle Scriptspackage.json
HighChild Processdist/autoresearch/runtime.js
HighShelldist/autoresearch/runtime.js
HighEntrypoint Build Divergencebridge/cli.cjs
HighSame File Env Network Executionscripts/release-boundary.mjs#virtual:normalized:round1
HighCredential Redirect Persistencebridge/cli.cjs
HighCommand Output Exfiltrationbridge/cli.cjs
HighHidden Inline Dependency Executionbridge/cli.cjs
HighSandbox Evasion Gated Capabilitydist/tools/lsp/servers.js
HighCloud Metadata Accessbridge/runtime-cli.cjs
Affected versions and remediation
This report applies to oh-my-claude-sisyphus@5.7.26.
See all versions of oh-my-claude-sisyphus for other recorded verdicts.
- Review the evidence and your use of oh-my-claude-sisyphus@5.7.26 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.